© 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. 39886
    Prev
    Next
    INDEX
    Explanations

    around

    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
    ,
    -0.69
     
    -0.65
    .
    -0.60
     P
    -0.60
     around
    -0.59
     of
    -0.58
     at
    -0.57
     (
    -0.57
     I
    -0.56
     O
    -0.53
    POSITIVE LOGITS
    تقاوى
    1.45
    parsedMessage
    1.27
     незавершена
    1.24
    Vidite
    1.20
    Personendaten
    1.20
     Roskov
    1.19
     дописавши
    1.17
     propOrder
    1.16
    SourceChecksum
    1.16
     bezeichneter
    1.13
    Activations Density 0.123%

    No Known Activations