© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    .-

    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
     Vera
    -0.93
    arum
    -0.92
    tidae
    -0.86
    .-
    -0.74
    Vera
    -0.71
    inae
    -0.70
     millions
    -0.59
    ijan
    -0.57
     casual
    -0.57
     sleep
    -0.55
    POSITIVE LOGITS
    theless
    0.68
    soever
    0.65
    LookAnd
    0.64
    ]")]
    0.63
    parsedMessage
    0.63
    quelles
    0.60
    middels
    0.59
     Audiodateien
    0.57
    okovic
    0.57
     fön
    0.56
    Activations Density 0.192%

    No Known Activations