© 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. 0-CLT-HP
    7. 97605
    Prev
    Next
    INDEX
    Explanations

    Causation

    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
    ,
    -0.84
     therefore
    -0.75
     thus
    -0.73
     daher
    -0.66
    Therefore
    -0.65
    therefore
    -0.65
     donc
    -0.62
     Therefore
    -0.62
    thus
    -0.61
    Thus
    -0.61
    POSITIVE LOGITS
    ⓧ
    0.60
     MSN
    0.58
     StringField
    0.58
     parietal
    0.57
    <bos>
    0.57
     Altri
    0.56
     Dipl
    0.54
     MSD
    0.54
    .’”
    0.53
     Forza
    0.53
    Activations Density 0.024%

    No Known Activations