© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4645
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hit" and its variants, indicating references to actions or impacts

    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
    Excerpt
    -0.69
     généraux
    -0.65
     Gull
    -0.63
    westen
    -0.58
    Otro
    -0.56
    贼
    -0.56
     menga
    -0.56
    verständnis
    -0.55
    gląda
    -0.55
    הערות
    -0.54
    POSITIVE LOGITS
     hits
    1.54
     hit
    1.49
     hitting
    1.48
     HIT
    1.43
     Hits
    1.42
    Hit
    1.41
     strikes
    1.38
     Hit
    1.37
     Strikes
    1.37
    hit
    1.36
    Activations Density 0.174%

    No Known Activations