Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 98177
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical text

    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
     PID
    -0.66
     threats
    -0.59
     deschis
    -0.59
    ide
    -0.55
    hell
    -0.54
    PID
    -0.53
     Secund
    -0.52
     threatening
    -0.52
    TextSpan
    -0.52
    hells
    -0.52
    POSITIVE LOGITS
    arranty
    0.65
    ThroughAttribute
    0.60
    OVERR
    0.59
    TestingModule
    0.59
    NOPQRST
    0.55
    schaft
    0.55
    Warranty
    0.54
    undred
    0.54
     immédi
    0.53
    ircraft
    0.53
    Activations Density 1.789%

    No Known Activations