© 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. 5-CLT-HP
    7. 2178
    Prev
    Next
    INDEX
    Explanations

    of

    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
    SBATCH
    -0.69
    NUMX
    -0.62
    ñores
    -0.60
    Portale
    -0.60
     يتيمه
    -0.57
     vœux
    -0.53
     rumahnya
    -0.53
     devenus
    -0.53
     niega
    -0.52
     hjälp
    -0.51
    POSITIVE LOGITS
     and
    0.75
     or
    0.70
    +#+#
    0.63
    ,
    0.59
    CPtr
    0.57
     –
    0.57
    DBNull
    0.55
     -
    0.54
    localctx
    0.53
    —
    0.52
    Activations Density 0.001%

    No Known Activations