© 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. 17437
    Prev
    Next
    INDEX
    Explanations

    references to the speaker or group involved in the discussion

    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
    torio
    -0.67
     '{@
    -0.59
    ']));
    -0.56
    XDECREF
    -0.55
    writeByte
    -0.55
    Hauptartikel
    -0.55
    enumi
    -0.53
     Parcelable
    -0.53
    GeneratedMessage
    -0.52
    NamedQueries
    -0.51
    POSITIVE LOGITS
    脚注の使い方
    0.71
     IBOutlet
    0.69
    adget
    0.68
    staun
    0.68
    plr
    0.68
    PhysRev
    0.67
    phalt
    0.65
    clusal
    0.64
    getDoctrine
    0.64
    raisemb
    0.63
    Activations Density 0.003%

    No Known Activations