© 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. 20-CLT-HP
    7. 72576
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
     فريبيس
    -0.92
     EconPapers
    -0.89
    RenderAtEndOf
    -0.88
    ########.
    -0.86
    NegativeButton
    -0.83
    NOPQRST
    -0.82
    PreferredItem
    -0.81
    LookAnd
    -0.81
     estekak
    -0.81
     myſelf
    -0.79
    POSITIVE LOGITS
     Am
    0.57
    Am
    0.50
     ga
    0.49
     Mur
    0.44
    gir
    0.44
    buffalo
    0.42
     G
    0.42
     cross
    0.41
    Mur
    0.40
    huk
    0.40
    Activations Density 0.000%

    No Known Activations