© 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. 4-CLT-HP
    7. 4496
    Prev
    Next
    INDEX
    Explanations

    0

    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
    IntoConstraints
    -0.71
     Administrativna
    -0.70
    ungsbedingungen
    -0.70
     مرئيه
    -0.69
    וויק
    -0.63
    OGND
    -0.63
    Datuak
    -0.62
     nakalista
    -0.61
    styleType
    -0.61
    RenderAtEndOf
    -0.61
    POSITIVE LOGITS
    Przypisy
    0.53
     cref
    0.51
    󠁿
    0.46
     specialises
    0.46
    =[];
    0.44
     Shuk
    0.44
     specialised
    0.42
     utilising
    0.41
    ^\
    0.40
    äk
    0.40
    Activations Density 0.295%

    No Known Activations