© 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. 5-CLT-HP
    7. 5557
    Prev
    Next
    INDEX
    Explanations

    technical/scientific content

    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
    enumi
    -0.72
    enumii
    -0.59
    UIControlState
    -0.56
    extAlignment
    -0.53
    ="@+
    -0.53
    Välislingid
    -0.51
    Carriera
    -0.50
    Manbalar
    -0.50
    stylers
    -0.50
    providedIn
    -0.49
    POSITIVE LOGITS
     we
    0.59
    parsedMessage
    0.57
     Monfieur
    0.56
     you
    0.53
     ourselves
    0.52
    arranging
    0.51
     Efq
    0.49
     بودند
    0.49
     داشتند
    0.49
    govina
    0.48
    Activations Density 0.001%

    No Known Activations