© 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. 4-CLT-HP
    7. 4552
    Prev
    Next
    INDEX
    Explanations

    vian

    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
    toHaveBeenCalled
    -0.68
    +#+#
    -0.66
    Datuak
    -0.62
    MergeFrom
    -0.61
    __":
    -0.57
     GLP
    -0.56
     ExecuteAsync
    -0.55
    SequentialGroup
    -0.54
     gemis
    -0.53
    fuls
    -0.52
    POSITIVE LOGITS
    ter
    0.59
    цездатний
    0.53
    ništ
    0.50
    таратура
    0.48
     FormsModule
    0.47
    my
    0.44
    StoryboardSegue
    0.43
    ters
    0.43
     clearColor
    0.42
    TextAppearance
    0.42
    Activations Density 0.001%

    No Known Activations