© 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. 5-CLT-HP
    7. 2180
    Prev
    Next
    INDEX
    Explanations

    ous

    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
     …
    -0.50
     ...
    -0.42
    </strong>
    -0.41
     getArguments
    -0.40
     vē
    -0.40
     löytyy
    -0.40
     viata
    -0.40
     vagyok
    -0.39
     néz
    -0.38
     partea
    -0.38
    POSITIVE LOGITS
    ########.
    0.96
    .
    0.93
    Personensuche
    0.90
    LookAnd
    0.88
    ValueStyle
    0.87
     Audiodateien
    0.84
     HasFactory
    0.82
    :].
    0.81
    intios
    0.81
     الحره
    0.81
    Activations Density 0.026%

    No Known Activations