© 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. 5-CLT-HP
    4. 95204
    Prev
    Next
    INDEX
    Explanations

    development

    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
     Olympedia
    -0.52
     Réponses
    -0.51
    rieks
    -0.51
    mbols
    -0.49
    JNIEnv
    -0.49
    ultat
    -0.48
    imedia
    -0.47
    erequisites
    -0.45
    theoremstyle
    -0.45
    istungen
    -0.44
    POSITIVE LOGITS
     ArrayAdapter
    0.61
     nakalista
    0.60
    theless
    0.58
     unfolding
    0.56
     GeoNames
    0.56
     pulumi
    0.54
    DataPropertyName
    0.54
    rungsseite
    0.53
    Trama
    0.53
     stalking
    0.52
    Activations Density 0.014%

    No Known Activations