© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5750
    Prev
    Next
    INDEX
    Explanations

    legal and liability-related terms associated with damages and consequences

    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
    ArgsConstructor
    -0.86
    DebuggerNonUser
    -0.69
     vastaan
    -0.69
    UnusedPrivate
    -0.66
    WritableDatabase
    -0.66
    __':
    -0.66
     importar
    -0.64
     FirebaseAuth
    -0.63
    SupportActionBar
    -0.63
     Мексичка
    -0.61
    POSITIVE LOGITS
     DAMAGES
    0.55
    EMPL
    0.51
     indirect
    0.50
     חיצוניים
    0.49
    lev
    0.49
     Kost
    0.49
    IDENTAL
    0.48
    iedy
    0.47
    Kost
    0.47
    emed
    0.46
    Activations Density 0.004%

    No Known Activations