© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93763
    Prev
    Next
    INDEX
    Explanations

    code

    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
    rungsseite
    -0.65
    ArgsConstructor
    -0.61
     tartalomajánló
    -0.58
     @"/
    -0.57
    SourceChecksum
    -0.55
    ConstraintMaker
    -0.54
    AndEndTag
    -0.53
    InSection
    -0.52
    Scopes
    -0.51
    SuppressLint
    -0.50
    POSITIVE LOGITS
    rinos
    0.55
    RIN
    0.55
    vinas
    0.54
    ]='\
    0.50
    clin
    0.47
    Földrajzportál
    0.47
    Spoljašnje
    0.47
    Климат
    0.47
     חיצוניים
    0.47
    Vidu
    0.46
    Activations Density 0.076%

    No Known Activations