© 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. 14666
    Prev
    Next
    INDEX
    Explanations

    instances of functions or method calls in code

    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
     didst
    -0.72
     Hopf
    -0.63
     diritto
    -0.62
     renseignements
    -0.62
     purpoſe
    -0.60
    њ
    -0.60
     preſent
    -0.59
     Shaksp
    -0.59
     houſe
    -0.59
     kangaroo
    -0.58
    POSITIVE LOGITS
     the
    0.90
    RTEX
    0.76
    RTEE
    0.75
    Gön
    0.74
     kiệm
    0.72
    ")));
    0.72
    [])
    0.71
    WriteBarrier
    0.71
     beginnetje
    0.69
    IVEREF
    0.68
    Activations Density 0.056%

    No Known Activations