© 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. 92803
    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
    SerializedSize
    -0.67
    ScopeManager
    -0.66
    UserScript
    -0.64
    icitis
    -0.63
    RTEE
    -0.63
     Picchu
    -0.63
    NESSEE
    -0.62
     LoginComponent
    -0.60
    unzel
    -0.59
    :][
    -0.58
    POSITIVE LOGITS
    enumi
    0.55
     réponse
    0.50
    Above
    0.48
     quæ
    0.47
     habet
    0.46
     tovább
    0.45
    better
    0.44
     naturels
    0.44
     importar
    0.44
     naturais
    0.44
    Activations Density 0.043%

    No Known Activations