© 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. 239
    Prev
    Next
    INDEX
    Explanations

    language related to abstract academic or scientific concepts and arguments

    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
    SourceChecksum
    -0.79
     مرئيه
    -0.75
     typelib
    -0.69
    RegressionTest
    -0.63
    ThroughAttribute
    -0.58
     komer
    -0.58
    Péri
    -0.57
    tagHelperRunner
    -0.56
    ”…
    -0.53
     romanti
    -0.52
    POSITIVE LOGITS
     abstracta
    0.60
     constitutive
    0.59
     onto
    0.54
     Möglich
    0.53
     instantiated
    0.53
     account
    0.53
    liciter
    0.52
     epistem
    0.51
     stipul
    0.51
    criptions
    0.50
    Activations Density 0.878%

    No Known Activations