© 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. 4-CLT-HP
    7. 3258
    Prev
    Next
    INDEX
    Explanations

    varied writing excerpts

    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
    θλη
    -0.46
     heuer
    -0.42
     ovp
    -0.41
     gql
    -0.41
     '\\;'
    -0.40
     transfieras
    -0.40
    DotNetBar
    -0.40
    ăzi
    -0.39
    retter
    -0.37
    itosti
    -0.37
    POSITIVE LOGITS
     صوتيه
    0.69
    Jeez
    0.67
    (||
    0.65
    jstor
    0.65
    riente
    0.63
     estekak
    0.59
    orcid
    0.58
    исленность
    0.58
    rizona
    0.58
    posal
    0.58
    Activations Density 0.003%

    No Known Activations