© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94542
    Prev
    Next
    INDEX
    Explanations

    delimiters

    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
     Monfieur
    -1.15
     itſelf
    -1.12
     ―――――
    -1.09
     nahilalakip
    -1.09
     –,
    -1.03
     myſelf
    -1.03
    脚注の使い方
    -1.02
     ProtoMessage
    -1.02
     Majefty
    -0.94
    دانشنامهٔ
    -0.94
    POSITIVE LOGITS
     
    1.13
     a
    0.77
     I
    0.75
     The
    0.74
     F
    0.72
     A
    0.71
     B
    0.71
     .
    0.71
     E
    0.70
     $\
    0.70
    Activations Density 0.321%

    No Known Activations