© 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. 92020
    Prev
    Next
    INDEX
    Explanations

    return, this

    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
     AssemblyCulture
    -0.67
     betweenstory
    -0.63
    كويكب
    -0.60
    LookAnd
    -0.57
    ItemBackground
    -0.56
    RTLD
    -0.54
    withIdentifier
    -0.54
    UAWEI
    -0.53
    Demografie
    -0.52
     Naming
    -0.51
    POSITIVE LOGITS
     said
    0.60
     introduced
    0.60
     deployed
    0.56
     implemented
    0.56
     installed
    0.56
     considered
    0.56
     removed
    0.54
     taken
    0.53
     being
    0.53
     much
    0.53
    Activations Density 0.003%

    No Known Activations