© 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. 45084
    Prev
    Next
    INDEX
    Explanations

    Hy

    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
    Hy
    -1.05
     Hy
    -1.02
    hy
    -0.97
     hy
    -0.94
    EndInit
    -0.80
    StoryboardSegue
    -0.79
     nahilalakip
    -0.74
    HY
    -0.73
     disambiguazione
    -0.73
    VolleyError
    -0.71
    POSITIVE LOGITS
    s
    0.58
    day
    0.56
    der
    0.56
    k
    0.53
    say
    0.51
    don
    0.50
    kian
    0.49
    ders
    0.48
    scal
    0.48
    ting
    0.47
    Activations Density 0.220%

    No Known Activations