© 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. 1-CLT-HP
    7. 12379
    Prev
    Next
    INDEX
    Explanations

    ec

    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
    νού
    -0.59
    ν
    -0.59
    enumii
    -0.59
    خة
    -0.59
     lentils
    -0.58
     handker
    -0.56
    formKey
    -0.56
     straps
    -0.56
     snippetHide
    -0.56
    ########.
    -0.55
    POSITIVE LOGITS
    TagMode
    0.61
    prepareStatement
    0.52
    CheckedChanged
    0.48
    TargetException
    0.47
     cref
    0.45
    toPromise
    0.44
    AccessorTable
    0.41
    vailability
    0.41
     IDisposable
    0.40
    ubles
    0.40
    Activations Density 0.028%

    No Known Activations