© 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. 93956
    Prev
    Next
    INDEX
    Explanations

    self

    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
     self
    -1.30
    self
    -0.97
     Self
    -0.91
    Self
    -0.84
     
    -0.77
    </strong>
    -0.71
     SELF
    -0.66
    .
    -0.63
     (
    -0.62
     not
    -0.62
    POSITIVE LOGITS
     Roskov
    0.99
    
    0.98
    Vidite
    0.94
     nahilalakip
    0.93
     متعلقه
    0.92
    lossians
    0.91
    MLLoader
    0.88
    abetes
    0.86
     photolibrary
    0.85
    afficheront
    0.85
    Activations Density 0.067%

    No Known Activations