© 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. 1-CLT-HP
    7. 378
    Prev
    Next
    INDEX
    Explanations

    Medicine/Science

    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
    OGND
    -0.86
     незавершена
    -0.79
    فایل‌لار
    -0.70
     Administrativna
    -0.68
     виправивши
    -0.67
     propOrder
    -0.66
     snippetHide
    -0.65
    featureID
    -0.65
    AnimationsModule
    -0.65
    +:+
    -0.64
    POSITIVE LOGITS
    esModule
    0.53
     of
    0.47
     nakalista
    0.43
    endphp
    0.42
    atasi
    0.42
     SELF
    0.41
    self
    0.41
    Geograf
    0.40
     Self
    0.40
    assertNull
    0.40
    Activations Density 0.014%

    No Known Activations