© 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. 97646
    Prev
    Next
    INDEX
    Explanations

    Location data or code

    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
    ny
    -1.07
     Ny
    -1.05
    Ny
    -0.98
     ny
    -0.98
     dish
    -0.90
    dish
    -0.90
     tenant
    -0.81
    nya
    -0.79
    ently
    -0.77
    tenant
    -0.76
    POSITIVE LOGITS
    <bos>
    0.62
    LookAnd
    0.50
     Targ
    0.49
    PullParser
    0.49
     contingency
    0.48
    mbres
    0.46
     marines
    0.45
    ambi
    0.44
     Contingency
    0.44
     continúas
    0.43
    Activations Density 0.281%

    No Known Activations