© 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. 44207
    Prev
    Next
    INDEX
    Explanations

    mt

    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
     Jug
    -1.21
    Jug
    -1.11
    jug
    -0.84
     myſelf
    -0.82
     itſelf
    -0.81
     raiſ
    -0.73
     tranſ
    -0.71
     themſelves
    -0.69
     uſed
    -0.69
     pleaſure
    -0.69
    POSITIVE LOGITS
    nose
    0.59
    NameInMap
    0.57
    gling
    0.57
     End
    0.52
    EndContext
    0.52
    SBATCH
    0.51
     An
    0.50
     Mon
    0.50
    ISupport
    0.50
     Tel
    0.49
    Activations Density 0.194%

    No Known Activations