© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1235
    Prev
    Next
    INDEX
    Explanations

    appeal

    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
     appeal
    -1.52
    appeal
    -1.42
     appealing
    -1.19
    Appeal
    -1.13
     Appeal
    -1.11
     appealed
    -1.08
     appeals
    -1.06
     APPEAL
    -1.04
    appe
    -1.01
    Appe
    -0.87
    POSITIVE LOGITS
    jspb
    0.59
    abestanden
    0.57
    سطس
    0.52
    rd
    0.50
    rrggbb
    0.50
     Signalez
    0.50
    aarrggbb
    0.50
     calculées
    0.49
    ROIT
    0.48
    ConstraintMaker
    0.48
    Activations Density 0.122%

    No Known Activations