© 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. 5088
    Prev
    Next
    INDEX
    Explanations

    of

    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
     a
    -0.47
    のですか
    -0.46
    からです
    -0.45
    ResumeLayout
    -0.44
    providedIn
    -0.44
     '*':
    -0.44
    idon
    -0.43
     '+':
    -0.43
    izarse
    -0.43
     Dijk
    -0.42
    POSITIVE LOGITS
    windowFixed
    0.65
    SerializedSize
    0.62
    Referencer
    0.60
     חיצוניים
    0.59
    Rujukan
    0.57
    طلحات
    0.57
    GenerationType
    0.56
    gestone
    0.56
    HasColumnType
    0.54
     chì
    0.54
    Activations Density 0.004%

    No Known Activations