© 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. 94146
    Prev
    Next
    INDEX
    Explanations

    assurance

    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
    es
    -0.85
    ES
    -0.65
     of
    -0.57
    hes
    -0.56
    ge
    -0.52
     introduced
    -0.51
    ors
    -0.50
     es
    -0.49
    rd
    -0.49
     understood
    -0.49
    POSITIVE LOGITS
     myſelf
    1.10
     doubtnut
    1.00
     Theſe
    0.97
    ^(@)
    0.96
     themſelves
    0.92
     itſelf
    0.91
     ―――――
    0.89
     againſt
    0.86
     whoſe
    0.86
     uſed
    0.85
    Activations Density 0.139%

    No Known Activations