© 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. 92192
    Prev
    Next
    INDEX
    Explanations

    desert

    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
     UIAlert
    -0.74
    HostException
    -0.71
    ValueGeneration
    -0.71
     forest
    -0.69
     SDLK
    -0.69
     desert
    -0.69
    tadır
    -0.68
    ientôt
    -0.68
    NUMX
    -0.68
    Portail
    -0.67
    POSITIVE LOGITS
    ing
    0.49
    land
    0.46
    ium
    0.44
    relevant
    0.43
    ular
    0.42
    an
    0.42
    ics
    0.40
     arrears
    0.39
    us
    0.39
    um
    0.39
    Activations Density 0.188%

    No Known Activations