© 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. 94155
    Prev
    Next
    INDEX
    Explanations

    of/or

    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
    DispatchToProps
    -0.61
     consultato
    -0.57
     שוליים
    -0.56
    HtmlAttribute
    -0.56
    wußt
    -0.53
    ustimmung
    -0.52
    悴
    -0.52
     (§
    -0.52
    ^(@)
    -0.52
    __":
    -0.52
    POSITIVE LOGITS
     
    0.74
    4
    0.72
    7
    0.71
    6
    0.69
    5
    0.68
    9
    0.68
    1
    0.67
    8
    0.66
    3
    0.64
    0
    0.62
    Activations Density 0.154%

    No Known Activations