© 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. 0-CLT-HP
    7. 93851
    Prev
    Next
    INDEX
    Explanations

    names

    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
    LookAnd
    -0.83
    principalTable
    -0.69
     समीक्षक
    -0.68
    Geplaatst
    -0.62
     beginnetje
    -0.61
    InputTagHelper
    -0.59
     betweenstory
    -0.57
    RTDA
    -0.57
    KURZBESCHREIBUNG
    -0.57
    adpleegd
    -0.56
    POSITIVE LOGITS
     étrangère
    0.46
    horst
    0.45
     J
    0.40
     W
    0.40
    entación
    0.39
    PostalCode
    0.38
     jefe
    0.37
     africaine
    0.36
     elettrica
    0.36
    elaar
    0.36
    Activations Density 0.051%

    No Known Activations