© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    mentions of following or tracking actions

    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
     Yag
    -0.78
     McCarty
    -0.77
    oldValue
    -0.75
    tské
    -0.69
    besar
    -0.67
     Urqu
    -0.66
     Pemberton
    -0.66
     Jacobsen
    -0.65
     Veld
    -0.65
     способ
    -0.64
    POSITIVE LOGITS
     Follows
    1.66
    follow
    1.56
     follows
    1.48
     follow
    1.48
     FOLLOW
    1.46
    follows
    1.45
    Follow
    1.41
     Follow
    1.39
    Followed
    1.34
     Followed
    1.34
    Activations Density 0.525%

    No Known Activations