© 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. 3476
    Prev
    Next
    INDEX
    Explanations

    each

    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
    ArgsConstructor
    -0.84
    tagHelperRunner
    -0.81
    ContentAsync
    -0.66
     esternos
    -0.57
    URLException
    -0.56
    nloa
    -0.56
    Naphthalene
    -0.55
     AppDelegate
    -0.55
    ]='\
    -0.54
    omentos
    -0.54
    POSITIVE LOGITS
     חיצוניים
    0.56
     with
    0.54
     bears
    0.49
     blessed
    0.44
    άνει
    0.43
     employing
    0.43
    hombres
    0.43
     deals
    0.43
     canlynol
    0.43
     accompanied
    0.42
    Activations Density 0.003%

    No Known Activations