© 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. 0-CLT-HP
    7. 42698
    Prev
    Next
    INDEX
    Explanations

    isol

    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
    GraphicsUnit
    -0.88
     Isol
    -0.82
    isol
    -0.81
    EndContext
    -0.75
    TagMode
    -0.70
    MENAFN
    -0.67
    EndGlobalSection
    -0.65
    BeginContext
    -0.64
     linkovi
    -0.64
    ibase
    -0.63
    POSITIVE LOGITS
    uminate
    0.49
    klart
    0.48
    </tfoot>
    0.46
    sld
    0.44
    zake
    0.44
    сторія
    0.43
    Ligações
    0.42
    chestra
    0.42
    skap
    0.41
     sœurs
    0.41
    Activations Density 0.083%

    No Known Activations