© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97718
    Prev
    Next
    INDEX
    Explanations

    discriminator

    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
    StructEnd
    -0.73
    rateful
    -0.67
    ientôt
    -0.65
     ioutil
    -0.63
    गत
    -0.57
    ikä
    -0.55
     ComVisible
    -0.55
    änning
    -0.54
    polazione
    -0.54
    skosten
    -0.54
    POSITIVE LOGITS
     adipis
    0.77
    RenderAtEndOf
    0.65
    er
    0.61
    ValueStyle
    0.59
    ness
    0.58
    __((
    0.58
     Reverso
    0.56
    ity
    0.55
    ant
    0.53
     snippetHide
    0.52
    Activations Density 1.642%

    No Known Activations