© 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. 1-CLT-HP
    7. 10462
    Prev
    Next
    INDEX
    Explanations

    ita

    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
     predation
    -0.82
    OGND
    -0.59
    Administrator
    -0.57
    EndInit
    -0.56
    DockStyle
    -0.56
    administrator
    -0.54
     Administrators
    -0.54
    andidaten
    -0.54
     imageNamed
    -0.52
    GIH
    -0.51
    POSITIVE LOGITS
     risk
    0.58
     pressure
    0.55
    vskip
    0.52
     aprons
    0.51
     rates
    0.48
    对了
    0.47
    risk
    0.47
     events
    0.47
    pressure
    0.47
     guilt
    0.46
    Activations Density 0.054%

    No Known Activations