© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1747
    Prev
    Next
    INDEX
    Explanations

    due

    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
    ʁ
    -0.36
    ↵
    -0.35
    <code>
    -0.32
     appunto
    -0.31
    df
    -0.31
     c
    -0.31
    <u>
    -0.30
     die
    -0.30
     .
    -0.29
    I
    -0.29
    POSITIVE LOGITS
    principalTable
    1.06
     Walkover
    1.01
    writeFieldEnd
    0.95
    InjectAttribute
    0.94
     مشين
    0.93
     linkovi
    0.91
     disambiguazione
    0.91
    saraba
    0.91
    ########.
    0.90
     विश्वसनीयता
    0.89
    Activations Density 0.013%

    No Known Activations