© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92124
    Prev
    Next
    INDEX
    Explanations

    Scream

    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
     Principle
    -0.75
    Principle
    -0.63
    mmons
    -0.63
     Houſe
    -0.59
     Jefus
    -0.58
     primaire
    -0.57
     Monfieur
    -0.57
     urbain
    -0.57
     Mank
    -0.56
     Majefty
    -0.56
    POSITIVE LOGITS
    ed
    0.73
    er
    0.69
    ers
    0.59
    ier
    0.57
    AIRES
    0.57
    서는
    0.55
    Архівовано
    0.54
     mark
    0.51
    erg
    0.51
    ER
    0.50
    Activations Density 1.450%

    No Known Activations