© 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. 12-RES-MATRYOSHKA-DC
    7. 15219
    Prev
    Next
    INDEX
    Explanations

    technical terms and data related to measurements and analysis in a scientific context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    <bos>
    -0.52
     überhaupt
    -0.46
     Poly
    -0.44
     note
    -0.44
    DR
    -0.44
    note
    -0.43
    Note
    -0.41
     Note
    -0.40
    繫
    -0.39
    sistency
    -0.39
    POSITIVE LOGITS
     Theſe
    0.84
    jooq
    0.71
     كومونز
    0.71
    脚注の使い方
    0.68
    ostante
    0.66
    MigrationBuilder
    0.66
    Alike
    0.65
    MessageTagHelper
    0.65
     Majefty
    0.65
    клопе
    0.64
    Activations Density 0.374%

    No Known Activations