© 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. 97986
    Prev
    Next
    INDEX
    Explanations

    is

    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
     admittedly
    -0.71
     really
    -0.65
     honestly
    -0.63
     hadn
    -0.62
    Really
    -0.59
     myſelf
    -0.59
    还真
    -0.57
    Honestly
    -0.57
     hasn
    -0.56
     haven
    -0.56
    POSITIVE LOGITS
    DockStyle
    0.63
    parsedMessage
    0.63
    __*/
    0.59
    hyrchwyd
    0.59
    NameInMap
    0.58
    ="@+
    0.57
     EconPapers
    0.57
    rrggbb
    0.57
     inoltre
    0.53
    fromnode
    0.52
    Activations Density 0.028%

    No Known Activations