© 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. 45076
    Prev
    Next
    INDEX
    Explanations

    logical

    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
     tuning
    -0.65
     workshop
    -0.63
     logical
    -0.63
     tuned
    -0.61
    tuned
    -0.61
    tune
    -0.60
     justified
    -0.60
     tune
    -0.60
    Tune
    -0.59
     vein
    -0.58
    POSITIVE LOGITS
    KEYCODE
    0.67
     AppCompat
    0.64
    يكب
    0.60
    putExtra
    0.58
    ngdoc
    0.56
     ANCHE
    0.56
    amethasone
    0.55
     WaitForSeconds
    0.54
    GEBURTSDATUM
    0.54
    thest
    0.53
    Activations Density 0.100%

    No Known Activations