© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 333
    Prev
    Next
    INDEX
    Explanations

    descriptions of genes in scientific writing, including being/having a demonstrated or reported property

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.65
    AxisAlignment
    -0.60
    almaz
    -0.60
     VIAF
    -0.58
    istoitu
    -0.55
    IntoConstraints
    -0.54
    migrationBuilder
    -0.53
    MessageOf
    -0.53
    addCriterion
    -0.53
    indelijk
    -0.52
    POSITIVE LOGITS
     commonly
    0.84
     frequently
    0.81
     widely
    0.80
     thought
    0.78
     believed
    0.73
    frequently
    0.70
    commonly
    0.70
     Commonly
    0.69
     recognized
    0.69
     Frequently
    0.68
    Activations Density 1.543%

    No Known Activations