© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75604
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ThroughAttribute
    -0.72
    verifyException
    -0.71
     raiſ
    -0.68
     ſtand
    -0.66
     becauſe
    -0.64
     ſta
    -0.64
     fhew
    -0.63
     Efq
    -0.63
     STAM
    -0.63
     salomon
    -0.62
    POSITIVE LOGITS
    PyExc
    0.48
    lice
    0.44
    CloseOperation
    0.42
    iastes
    0.41
    tite
    0.40
     πέ
    0.38
    ElementException
    0.38
    ָּ
    0.37
     AttributeSet
    0.37
     dedo
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.