© 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. 92748
    Prev
    Next
    INDEX
    Explanations

    deformity

    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
    tedly
    -0.55
    Itoa
    -0.55
     considérons
    -0.55
     Traduction
    -0.53
    matically
    -0.53
    ỳnh
    -0.52
    INATION
    -0.51
     تانيه
    -0.51
    crumb
    -0.51
    Litteratur
    -0.51
    POSITIVE LOGITS
    tanleria
    0.66
     Wikimedijinoj
    0.56
    htbp
    0.52
     puissiez
    0.50
     revés
    0.48
    PhysRevD
    0.47
    parsedMessage
    0.46
     ögon
    0.46
    GetAxis
    0.45
     saites
    0.45
    Activations Density 0.012%

    No Known Activations