© 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. 1-CLT-HP
    7. 14980
    Prev
    Next
    INDEX
    Explanations

    val

    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
     незавершена
    -0.76
    niająca
    -0.50
     supernatural
    -0.49
    تيجة
    -0.49
    tagHelperRunner
    -0.46
     FetchType
    -0.46
    anair
    -0.46
    行政区划
    -0.46
    idopsis
    -0.46
    GraphicsUnit
    -0.44
    POSITIVE LOGITS
     utafitiHapana
    0.69
     bastion
    0.55
    sag
    0.52
    مصادر
    0.51
    glTexCoord
    0.51
    rasser
    0.50
     racket
    0.50
     paramInt
    0.49
     inventors
    0.49
    OrEmpty
    0.49
    Activations Density 0.010%

    No Known Activations