© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97559
    Prev
    Next
    INDEX
    Explanations

    physical locations and project files

    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
    DockStyle
    -0.94
    tagHelperRunner
    -0.89
    LookAnd
    -0.88
    ModelAdmin
    -0.86
     незавершена
    -0.85
     createSlice
    -0.81
    InjectAttribute
    -0.80
    httphttps
    -0.79
     nakalista
    -0.79
    Portale
    -0.79
    POSITIVE LOGITS
     analysis
    0.61
     investigation
    0.55
    ’
    0.54
     conditions
    0.53
    '
    0.53
     condition
    0.52
     evaluation
    0.51
     characteristics
    0.49
     and
    0.47
     assessment
    0.47
    Activations Density 0.000%

    No Known Activations