© 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. 952
    Prev
    Next
    INDEX
    Explanations

    friends

    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
    with
    -0.47
    TintMode
    -0.45
     '\\;'
    -0.43
     kasarigan
    -0.42
    land
    -0.41
     ErrIntOverflow
    -0.41
     With
    -0.40
    리는
    -0.40
    보
    -0.40
     gé
    -0.39
    POSITIVE LOGITS
    tinyos
    0.69
     masts
    0.65
    </thead>
    0.63
    цездатний
    0.60
     denominator
    0.60
    istoitu
    0.59
    otheses
    0.58
     throats
    0.58
    tvguidetime
    0.57
     Agamemnon
    0.57
    Activations Density 0.002%

    No Known Activations