© 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. 5551
    Prev
    Next
    INDEX
    Explanations

    states

    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
    ISPR
    -0.58
    gles
    -0.46
    es
    -0.45
    면
    -0.45
    THISDAY
    -0.44
     don
    -0.43
    OSE
    -0.43
     eder
    -0.43
    ISE
    -0.42
    Ingestion
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.72
    rungsseite
    0.69
    RectangleBorder
    0.66
    exitRule
    0.66
    Tembelea
    0.64
    state
    0.64
    曖昧さ回避
    0.63
    ConstraintMaker
    0.63
    StructEnd
    0.63
    Diweddarwch
    0.62
    Activations Density 0.004%

    No Known Activations