© 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. 20-CLT-HP
    7. 74660
    Prev
    Next
    INDEX
    Explanations

    changes and distributions

    np_max-act-logits · 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
    Erstellt
    -0.56
     APC
    -0.53
    cmc
    -0.52
     McCar
    -0.52
     McCall
    -0.51
    APC
    -0.49
     CMC
    -0.49
    ml
    -0.47
    apc
    -0.47
    oplan
    -0.47
    POSITIVE LOGITS
     Normdatei
    0.68
    DeleteBehavior
    0.63
    principalColumn
    0.59
    脚注の使い方
    0.54
    uating
    0.53
    #+#
    0.52
    ributions
    0.51
     jedis
    0.51
     Tud
    0.51
    TypedDataSet
    0.51
    Activations Density 0.002%

    No Known Activations