© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45255
    Prev
    Next
    INDEX
    Explanations

    fluorescence

    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
     للاسماء
    -1.16
     GenerationType
    -1.15
     tartalomajánló
    -1.14
     snippetHide
    -1.13
    ſelves
    -1.13
    帖最后由
    -1.13
    Personensuche
    -1.12
     Roskov
    -1.10
     Савезне
    -1.09
    ſelf
    -1.07
    POSITIVE LOGITS
     in
    0.75
     and
    0.75
     for
    0.73
     of
    0.70
    .
    0.69
    ,
    0.69
     by
    0.65
     with
    0.65
     is
    0.63
     from
    0.60
    Activations Density 0.095%

    No Known Activations