© 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. 94903
    Prev
    Next
    INDEX
    Explanations

    AD/Ed

    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
     
    -1.18
     ed
    -1.07
     P
    -0.97
     (
    -0.97
     AD
    -0.94
    ,
    -0.94
     an
    -0.91
     K
    -0.91
     O
    -0.90
     Z
    -0.90
    POSITIVE LOGITS
     myſelf
    2.31
     itſelf
    2.22
     Monfieur
    2.13
     ―――――
    2.05
     Efq
    2.05
     raiſ
    2.03
     Majefty
    1.99
     doubtnut
    1.98
     Houſe
    1.96
     Anſ
    1.95
    Activations Density 0.301%

    No Known Activations