© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12200
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.50
     mxArray
    -0.41
     Wikiseite
    -0.36
     Inflate
    -0.35
    execSQL
    -0.35
     layui
    -0.35
    NameInMap
    -0.35
    enumi
    -0.34
     Morelos
    -0.34
     pasi
    -0.34
    POSITIVE LOGITS
     so
    0.64
    styleable
    0.59
     weiteren
    0.57
    ecution
    0.56
     így
    0.56
    respective
    0.56
    ButterKnife
    0.55
     respective
    0.54
     investigated
    0.54
    umably
    0.54
    Activations Density 0.060%

    No Known Activations