© 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. 0-CLT-HP
    4. 45222
    Prev
    Next
    INDEX
    Explanations

    emptied

    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
    PhysRevD
    -0.86
     Мексичка
    -0.85
     Савезне
    -0.81
     ComVisible
    -0.80
     SwitchCompat
    -0.77
     disparu
    -0.75
     ―――――
    -0.74
     IBC
    -0.71
    TypedDataSet
    -0.71
     doInBackground
    -0.71
    POSITIVE LOGITS
     Far
    0.54
     
    0.47
     part
    0.47
     Reg
    0.46
     B
    0.45
     Red
    0.44
     Part
    0.44
     Bark
    0.44
    akos
    0.44
     J
    0.43
    Activations Density 0.077%

    No Known Activations