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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98235
    Prev
    Next
    INDEX
    Explanations

    complete/completely

    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
    InjectAttribute
    -0.85
     تضيفلها
    -0.77
    ########.
    -0.74
    abestanden
    -0.72
    OGND
    -0.71
    ScopeManager
    -0.68
    UnusedPrivate
    -0.68
     ModelExpression
    -0.65
    rungsseite
    -0.65
    AccessorTable
    -0.65
    POSITIVE LOGITS
     or
    0.63
    jenner
    0.45
     ($
    0.41
    unref
    0.40
    Path
    0.40
     fit
    0.40
     (~
    0.39
     and
    0.38
    ($
    0.37
     useful
    0.37
    Activations Density 0.002%

    No Known Activations